Using the "Alibaba-NLP/gte-large-en-v1.5" embedding model, the text chunks will be vectorized and inserted into the ChromaDB vector database. The stored embeddings will be indexed and enriched with the metadata information.
Expected Output
Vector database that includes all the embedded text chunks with their metadata.
Description
Using the "Alibaba-NLP/gte-large-en-v1.5" embedding model, the text chunks will be vectorized and inserted into the ChromaDB vector database. The stored embeddings will be indexed and enriched with the metadata information.
Expected Output
Vector database that includes all the embedded text chunks with their metadata.
Implementation Plan
Implementation tasks